© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98945
    Prev
    Next
    INDEX
    Explanations

    cable television channels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incorporar
    -0.84
    cres
    -0.73
    iast
    -0.73
     impulsar
    -0.73
    higen
    -0.73
    さみ
    -0.71
     HOG
    -0.71
     بري
    -0.70
    sne
    -0.70
    koon
    -0.69
    POSITIVE LOGITS
     cable
    2.78
     Cable
    2.38
    Cable
    2.16
    cable
    2.05
     CABLE
    1.63
     cables
    1.62
    ケーブル
    1.50
     кабе
    1.48
     channel
    1.33
     câble
    1.31
    Activations Density 0.038%

    No Known Activations